The AI knowledge
glossary
Evaluating AI assistants means wading through jargon. Here is every concept that matters — RAG, embeddings, hybrid search, evals, MCP — explained plainly, with how each one works in practice.
Retrieval & Search
Embeddings
Numeric vector representations of text in which semantically similar passages end up close together, enabling search by meaning rather than exact words.
Hybrid Search
A retrieval strategy that combines semantic (vector) search with keyword (full-text) search and merges the results, capturing both meaning and exact matches.
Reciprocal Rank Fusion (RRF)
A way to merge ranked result lists into one by scoring each item on its position in each list, not its raw score, so different search methods can be combined.
Reranking
A second pass in which a stronger model re-scores the top search results against the question, so the passages that actually answer it rise to the top.
Semantic Search
Search that ranks results by meaning similarity between the query and documents, using embeddings, rather than by matching keywords.
Vector Database
A data store optimized for saving embedding vectors and finding the nearest neighbors of a query vector quickly, at scale.
Chunking
Splitting documents into smaller passages before embedding, so retrieval can return the precise section that answers a question rather than a whole page.
Generation & Quality
RAG (Retrieval-Augmented Generation)
An AI architecture that retrieves relevant documents from a trusted knowledge source and passes them to a language model, so answers are grounded in real content instead of the model's training data.
Hallucination
When a language model generates fluent, confident content that is factually wrong or entirely invented.
Grounding
Tying an AI answer to specific source content, so each claim comes from retrieved passages rather than the model's memory and can be checked against them.
Abstention
When an AI assistant declines to answer because its sources don't cover the question, and says so plainly instead of writing a confident guess.
Citations
Links from an AI answer back to the specific source documents used to generate it, allowing users to verify every claim.
Prompt Injection
An attack in which adversarial instructions are placed in user input or in retrieved content to manipulate an AI system into ignoring its rules or leaking data.
Eval (LLM Evaluation)
A systematic method for measuring the quality of AI-generated answers — often using a second model as a judge — so quality is tracked rather than assumed.
Support Metrics
Deflection Rate
The percentage of support questions resolved by self-service — typically an AI assistant — without creating a ticket or reaching a human agent.
Form Deflection
Answering a support request inside the contact form, before the ticket is sent, so customers with documented questions get help without waiting for an agent.
Knowledge Gap
A question real users ask that your content can't answer, or answers badly. Tracked over time, knowledge gaps become a ranked list of docs to write next.
Protocols & Infrastructure
Knowledge Base
A curated, indexed collection of an organization's knowledge — docs, wikis, tickets, repos — that an AI assistant retrieves from when answering questions.
MCP (Model Context Protocol)
An open protocol that lets AI applications (like IDE assistants) connect to external tools and data sources through a standard JSON-RPC interface.
llms.txt
A proposed standard for a markdown file at /llms.txt that gives AI tools a short summary of a site and links to its most useful pages, so they skip the clutter.
LLM Gateway
An abstraction layer between an application and language-model providers, allowing models to be swapped, routed, and managed without changing application code.
PII Masking
Finding personal data such as emails, phone numbers and card numbers in text, and replacing it with placeholders before an AI model reads it or it is stored.
Zero Data Retention
A setting under which an AI service answers a request and then discards it: the question and answer are not written to history, logs or traces.
See the concepts in action
Connect your docs and watch retrieval, grounding, and citations work on your own content — free, no credit card required.
Free to start · No credit card required